YAML Metadata Error:"license" must be one of [apache-2.0, mit, openrail, bigscience-openrail-m, creativeml-openrail-m, bigscience-bloom-rail-1.0, bigcode-openrail-m, afl-3.0, artistic-2.0, bsl-1.0, bsd, bsd-2-clause, bsd-3-clause, bsd-3-clause-clear, c-uda, cc, cc0-1.0, cc-by-2.0, cc-by-2.5, cc-by-3.0, cc-by-4.0, cc-by-sa-3.0, cc-by-sa-4.0, cc-by-nc-2.0, cc-by-nc-3.0, cc-by-nc-4.0, cc-by-nd-4.0, cc-by-nc-nd-3.0, cc-by-nc-nd-4.0, cc-by-nc-sa-2.0, cc-by-nc-sa-3.0, cc-by-nc-sa-4.0, cdla-sharing-1.0, cdla-permissive-1.0, cdla-permissive-2.0, wtfpl, ecl-2.0, epl-1.0, epl-2.0, etalab-2.0, eupl-1.1, eupl-1.2, agpl-3.0, gfdl, gpl, gpl-2.0, gpl-3.0, lgpl, lgpl-2.1, lgpl-3.0, isc, h-research, intel-research, lppl-1.3c, ms-pl, apple-ascl, apple-amlr, mpl-2.0, odc-by, odbl, openmdw-1.0, openrail++, osl-3.0, postgresql, ofl-1.1, ncsa, unlicense, zlib, pddl, lgpl-lr, deepfloyd-if-license, fair-noncommercial-research-license, llama2, llama3, llama3.1, llama3.2, llama3.3, llama4, grok2-community, gemma, unknown, other, array]

OpenSeek-Small-v1-SFT Documentation

Overview

We adopt the Octothinker to build strong reasoning foundations. Our model's training consists of two phases: a mid-training stable phase on 200 billion tokens from a mathematical corpus, followed by a 20 billion token decay phase. Subsequently, we fine-tune the model on the Infinity-Instruct dataset to achieve superior instruction-following capabilities. This model is open-sourced as a baseline for future experiments, such as enhancing the reasoning capabilities of small models through reinforcement learning. The model architecture is the same as the OpenSeek-Small-v1 model.